Mean-variance optimization with inferred regimes

The dynamics of financial time series display a cyclical behavior, and the performance of portfolio decisions based on the anticipated distribution of asset returns are sensitive to the alignment of the anticipated distribution and subsequently observed returns in cyclical markets. We consider that the financial market is characterized by factors, and we present a regime-switching auto-regressive model for macro-economic factors to reflect financial cycles. We then define a factor model for the distribution of asset returns, with returns depending on regimes through the factors. The dependence is on the regime sequence in successive periods, or the regime transition. The factor model structure is embedded in the asset expected returns and their corresponding covariance matrix. These regime-dependent parameters serve as the inputs to mean-variance optimization, thereby constructing portfolios adapted to the current market environment. A contrast between investment decisions based on the expectation over regimes or the selection of a single most likely (inferred) regime is provided. The improvements in portfolio performance are calibrated with market data on macroeconomic factors and exchange traded funds as investment instruments.